OpenAI
OpenAI’s rolling chat-latest alias for the latest Instant model used in ChatGPT, with text and image input.
At a glance
API model ID: chat-latest
Capabilities & boundaries
Tool support requires the appropriate API integration; a supported tool is not automatically active in every chat.
The model reference does not document configurable reasoning-effort choices or a default for this alias. Do not borrow settings from a similarly priced GPT model. Evaluate the current alias with a stable prompt set and record the test date so changes can be investigated.
Put it to work
Original examples from EZ Ai Assist. Adapt these to your task and the features available in your workspace.
Workflow 01
Use a stable rubric so alias changes can be evaluated fairly.
Answer the fixed test questions below using only the supplied reference notes. For each answer, include the relevant note ID and mark any unsupported part as unknown. Keep the same headings and length limits for every run. Finish with a list of ambiguities you encountered. Do not infer missing facts; this response will be compared with earlier dated runs using the same rubric.
Workflow 02
Make the intended audience and factual boundaries explicit.
Explain this product feature to the audience described below in 150 words or fewer. Use only the approved feature notes, preserve limitations, and define unfamiliar terms in plain language. Include one example only if the notes support it. Then identify any question the reader is likely to have that the notes cannot answer. Do not add capabilities or pricing promises.
Workflow 03
Use visible evidence to guide a human review.
Inspect this screenshot of a settings page and list five questions a new user might ask. For each question, cite the visible label or control that prompted it and suggest a short clarification using only the supplied product notes. Separate observations from assumptions. Do not claim that a control works or is broken without an interactive test.
Developer reference
These are OpenAI API reference prices, not EZ Ai Assist subscription prices.
View EZ Ai Assist plans| Token type | Price |
|---|---|
| Input | $5.00 |
| Cached input | $0.50 |
| Output | $30.00 |
Common questions
No. The API ID chat-latest is a rolling alias for the latest Instant model used in ChatGPT. The underlying snapshot changes regularly. Keep dated evaluation results if your workflow relies on consistent behavior.
ChatGPT Latest is the existing EZ Ai Assist catalog name. OpenAI’s developer reference uses Chat Latest and the API ID chat-latest. The public website URL is retained so existing links continue to work.
No. API access to a model does not provide the full ChatGPT product, its account memory, tools, or subscriptions. Tool availability depends on your integration, and EZ Ai Assist exposes its own supported features.
OpenAI recommends GPT-6 Astra for production API usage. A rolling alias is useful to evaluate current conversational behavior, but it requires regression checks and a plan for behavior changes.
The reviewed model reference marks both unsupported. Its rate-limit section still shows Batch queue values; those values should not override the explicit endpoint support statement.
The reference lists a 400,000-token context, 272,000 maximum input tokens, and 128,000 maximum output tokens. These are distinct limits, not a promise of answer completeness or app upload capacity.
The reference does not establish configurable effort choices for this alias. Its listed API prices are separate from EZ Ai Assist subscriptions. Check the app for available models and controls, and verify current provider documentation before integration.
Check the source
Specifications and API prices checked on . Example prompts and workflow advice are editorial guidance from EZ Ai Assist.
Same provider
OpenAI
GPT-6.1 Sol is OpenAI’s reasoning model for complex coding and professional work, with image input and a 1.05M-token context window.
OpenAI
GPT-6 Sol is an OpenAI model for complex coding and tool-assisted workflows, with image input and configurable reasoning.
OpenAI
GPT-6 Luna is an efficient OpenAI model for focused, high-volume tasks, with image input, structured outputs, and configurable reasoning.
OpenAI
GPT-6 Astra is an OpenAI model for complex reasoning, coding, and research, with image input and a 1.05M-token context window.